检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Glaszner, Lukas Zach, Martin Institute of Computer Graphics and Vision Graz University of Technology Inffeldgasse 16/II Graz8010 Austria Biomedical Imaging Group École polytechnique fédérale de Lausanne Lausanne1015 Switzerland Center for Biomedical Imaging Lausanne1015 Switzerland

Diffusion model have been successfully applied to many inverse problems, including MRI and CT reconstruction. Researchers typically re-purpose models originally designed for unconditional sampling without modifications. Using two different posterior sampling algorithms, we show empirically that such large networks are not necessary. Our smallest model, effectively a ResNet, performs almost as good as an attention U-Net on in-distribution reconstruction, while being significantly more robust towards distribution shifts. Furthermore, we introduce models trained on natural images and demonstrate that they can be used in both MRI and CT reconstruction, out-performing model trained on medical images in out-of-distribution cases. As a result of our findings, we strongly caution against simply re-using very large networks and encourage researchers to adapt the model complexity to the respective task. Moreover, we argue that a key step towards a general diffusion-based prior is training on natural images. © 2025, CC BY-SA.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Assessing the Societal Impacts of Emerging Distributed Intelligence Technologies

Assessing the Societal Impacts of Emerging Distributed Intel...

引用

2024 OPJU International Technology Conference on Smart Computing for Innovation and Advancement in Industry 4.0, OTCON 2024

作者： Khan, Irfan Alekhya, V. Rajalakshmi, B. Lakhanpal, Sorabh Alkhafaji, Mohammed Ayad Santhi, K. Lloyd Institute of Engineering & Technology Knowledge Park II Uttar Pradesh Greater Noida201306 India Institute of Aeronautical Engineering Hyderabad Dundigal India New Horizon College of Engineering Department of Computer Science Bangalore India Lovely Professional University Phagwara India National University of Science and Technology College of Technical Engineering Dhi Qar64001 Iraq St. Martin's Engineering College Dept. of It Telangana Secunderabad India

ISBN: (纸本)9798350373783

The Integrated Impact Assessment Framework (iiAF) is established in this study to examine how new distributed intelligence technologies (DIT) influence society. The framework comprises three powerful algorithms: SNDA, EIS, and EIAM. These illustrate DIT's various benefits. SNDA examines the complex social web, identifying hubs, community dynamics, and future trends. EIS predicts economic repercussions and provides GDP, expenditures, and job losses. computer faults and privacy are important ethical considerations for EIAM. These strategies paint a comprehensive picture of the effect. Fake data suggests the new strategy outperforms six others. The recommended strategy scores higher on significance, economic indicators, and ethics. The iiAF's DIT impact evaluation is more complete, educated, and responsible than other techniques. This work contributes to our understanding of the problem by proposing a flexible and resilient paradigm for dealing with the societal consequences of diverse technologies. The iiAF may demonstrate to politicians the immediate impacts of DIT adoption and discuss morality and society. The framework's holistic approach helps us understand how technology and society interact and evolve. © 2024 IEEE.

关键词： Inflation

来源：评论

学校读者我要写书评

暂无评论

Advanced Development on Real Time Monitoring of Bridges Using Wireless Fidelity 7

Advanced Development on Real Time Monitoring of Bridges Usin...

引用

7th International Conference on Circuit Power and Computing Technologies, ICCPCT 2024

作者： Ferlin Deva Shahila, D. Stephen, Valantina Padma Suresh, L. Ashwini, A. Shally, S.P. Anushia, R.M. Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of ECE Chennai India Saveetha School of Engineering Department of EEE Chennai Thandalam India Baselios Mathews II College of Engineering Computer Science and Engineering Kollam India DMI College of Engineering Department of ECE Chennai India DMI College of Engineering Department of CSE Chennai India

ISBN: (纸本)9798350372816

Wireless fidelity technology enables communication without the use of wires or connections between two or more people across large distances. Wireless technology encompasses communications that utilize both radio frequencies (RF) and infrared waves. The origin of wireless technology can be traced back to the invention of electromagnetic waves by the German physicist, geophysicist, and engineer, Heinrich Hertz. In the late nineteenth century, the commercial wireless telegraph service was established by the Italian entrepreneur Gugliello Marconi, more than half a century after the invention of the first commercially available wired telegraph in 1832. In the early twentieth century, Marconi was one of the pioneers of radio communications, transmitting radio signals to mobile receivers on ships. Wireless has always been more advanced than wired technology, and it's usually more expensive too, but it's also given us the added benefit of being able to move around and get and send *** this project, we'll be using MATLAB software to design and test the full model. We'll also be looking at wireless bridge health monitoring systems. ZigBee acts as the wireless network for short-range IEEE 802.11 communication between sensors in the bridge. © 2024 IEEE.

关键词： Zigbee

来源：评论

学校读者我要写书评

暂无评论

Advanced Simulation and Optimization Strategies in Thermo-Fluid Dynamics: A Deep Learning Approach to Enhancing Heat Transfer in Evaporative Cooling Systems

Advanced Simulation and Optimization Strategies in Thermo-Fl...

引用

2024 OPJU International Technology Conference on Smart Computing for Innovation and Advancement in Industry 4.0, OTCON 2024

作者： Rajalakshmi, B. Alekhya, V. Lakhanpal, Sorabh Khan, Irfan Munshid, Maha Chasib Maranan, Ramya New Horizon College of Engineering Department of Computer Science Bangalore India Institute of Aeronautical Engineering Hyderabad Dundigal India Lovely Professional University Phagwara India Lloyd Institute of Engineering & Technology Knowledge Park II Uttar Pradesh Greater Noida201306 India National University of Science and Technology Collage of Nursing Dhi Qar64001 Iraq Simats Saveetha School of Engineering Department of Research and Innovation Tamil Nadu Chennai602105 India

ISBN: (纸本)9798350373783

This article describes a novel technique to study and improve evaporative cooling systems to move heat better. The system uses the GA, CNN, LSTM, and FVM algorithms. Each thermofluid dynamics study approach provides something unique. The CNN approach independently acquires spatial information from raw modeling data to study fluid movement. Temporal linkages in sequential data reveal heat's movement over space and time via LSTM. GAN adds continuing antagonistic processes to the dataset, strengthening the model. GA adjusts GAN settings to improve data, whereas FVM simulates realistic fluid dynamics to improve heat transport. Ablation studies demonstrate each algorithm's distinct contributions and importance. Performance comparisons reveal that the recommended framework outperforms others in accuracy, processing time, memory utilization, convergence rate, resilience, and adaptability. Bar charts, line charts, pie charts, and histograms show how the recommended method compares to others. The framework is precise, efficient, and versatile, making it ideal for improving thermo-fluid dynamics models in evaporative cooling systems. Researchers and engineers seeking to improve heat transfer in evaporative cooling systems can utilize it. The proposed architecture is full and adaptable to thermal-fluid utilization issues. © 2024 IEEE.

关键词： Evaporative cooling systems

来源：评论

学校读者我要写书评

暂无评论

Multispectral Imaging for Differential Face Morphing Attack Detection: A Preliminary Study

Multispectral Imaging for Differential Face Morphing Attack ...

引用

IEEE Workshop on Applications of computer Vision (WACV)

作者： Raghavendra Ramachandra Sushma Venkatesh Naser Damer Narayan Vetrekar R. S. Gad Norwegian University of Science and Technology (NTNU) Gjøvik Norway AiBA AS Gjøvik Norway Fraunhofer Institute for Computer Graphics Research Germany School of Physical and Applied Sciences Goa University Goa India

Face morphing attack detection is emerging as an increasingly challenging problem owing to advancements in high-quality and realistic morphing attack generation. Reliable detection of morphing attacks is essential because these attacks are targeted for border control applications. This paper presents a multispectral framework for differential morphing-attack detection (D-MAD). The D-MAD methods are based on using two facial images that are captured from the ePassport (also called the reference image) and the trusted device (for example, Automatic Border Control (ABC) gates) to detect whether the face image presented in ePassport is morphed. The proposed multi-spectral D-MAD framework introduce a multispectral image captured as a trusted capture to acquire seven different spectral bands to detect morphing attacks. Extensive experiments were conducted on the newly created Multispectral Morphed Datasets (MSMD) with 143 unique data subjects that were captured using both visible and multispectral cameras in multiple sessions. The results indicate the superior performance of the proposed multispectral framework compared to visible images.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Real-time Settings and Their Transformation through Distributed Intelligence Communication Technologies

Real-time Settings and Their Transformation through Distribu...

引用

2024 OPJU International Technology Conference on Smart Computing for Innovation and Advancement in Industry 4.0, OTCON 2024

作者： Manjunatha Krishna, M. Hari Rai, Vijay Kumar Singh, Navdeep Kumar, Ashwani Habelalmateen, Mohammed I. New Horizon College of Engineering Department of Mechanical Engineering Bangalore India Institute of Aeronautical Engineering Hyderabad Dundigal India Ies College of Technology Department of Computer Science & Engineering M. P Bhopal India Lovely Professional University Phagwara India Lloyd Institute of Engineering & Technology Knowledge Park II Uttar Pradesh Greater Noida201306 India The Islamic University Najaf Iraq

ISBN: (纸本)9798350373783

Modern real-time settings and dispersed intelligence communication technologies require new solutions to improve efficiency, flexibility, and scalability. This research introduces dynamic edge-cloud orchestration for real-time intelligence. The approach uses the Dynamic Task Allocation Algorithm (DTAA), the Predictive Resource Scaling Algorithm (PRSA), and the Adaptive Communication Routing Algorithm. DTAA distributes work between edge devices and the cloud based on priority, processing time, and resources. PRSA estimates future resource needs, making edge and cloud scaling easier. ACRA adjusts communication routes based on latency, job priority, and network circumstances. We use numbers to compare the new strategy to six popular ones. These include SDA, TFA, RBI, FBA, and PRT. The proposed option outperforms the others in latency, scalability, security, reliability, freedom, and resource utilization. Due to its comprehensive framework for smart task assignment, resource management, and communication enhancement, DECO-RTI is a major advance in real-time settings. The approach can adapt to changing situations and automatically scale up resources, making it ahead of the curve for distributed intelligent communication systems. © 2024 IEEE.

关键词： Scalability

来源：评论

学校读者我要写书评

暂无评论

Light Direction Reconstruction Analysis and Improvement using XAI and CG 30

Light Direction Reconstruction Analysis and Improvement usin...

引用

30th International Conference in Central Europe on computer graphics, Visualization and computer Vision, WSCG 2022

作者： Miller, Markus Ronczka, Stefan Nischwitz, Alfred Westermann, Rüdiger Dept. of Computer Science and Mathematics University of Applied Sciences Munich Lothstr. 64 Bavaria MunichD-80335 Germany Computer Graphics and Visualization Technical University Munich Boltzmannstr. 3/II Bavaria GarchingD-85748 Germany w&co MediaServices GmbH & Co KG Charles-de-Gaulle-Str. 8 Bavaria MunichD-81737 Germany

ISBN: (纸本)9788086943336

With rapid advances in the field of deep learning, explainable artificial intelligence (XAI) methods were introduced to gain insight into internal procedures of deep neural networks. Information gathered by XAI methods can help to identify shortcomings in network architectures and image datasets. Recent studies, however, advise to handle XAI interpretations with care, as they can be unreliable. Due to this unreliability, this study uses meta information that is produced when applying XAI to enhance the architecture - and thus the prediction performance - of a recently published regression model. This model aimed to contribute to solving the photometric registration problem in the field of augmented reality by regressing the dominant light direction in a scene. Bypassing misleading XAI interpretations, the influence of synthetic training data, generated with different rendering techniques, is furthermore evaluated empirically. In conclusion, this study demonstrates how the prediction performance of the recently published model can be increased by improving the network architecture and training dataset. © 2022 University of West Bohemia. All rights reserved.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

First Workshop on User Perspectives in Human-Centred Artificial Intelligence (HCAI4U) 23

First Workshop on User Perspectives in Human-Centred Artific...

引用

15th Biannual Conference of the Italian SIGCHI Chapter: Crossing HCI and AI, CHItaly 2023

作者： De Luca, Ernesto William Purificato, Erasmo Boratto, Ludovico Marrone, Stefano Sansone, Carlo Institute of Technical and Business Information Systems Human-Centred AI Group Otto von Guericke University Magdeburg Germany Department of Mathematics and Computer Science University of Cagliari Italy Dipartimento di Ingegneria Elettrica e Delle Tecnologie dell'Informazione University of Naples Federico II Italy

ISBN: (纸本)9798400708060

The emerging concept of Human-Centred Artificial Intelligence (HCAI) involves the amplification, augmentation, empowerment, and enhancement of individuals. The goal of HCAI is to ensure that AI meets our needs while also operating transparently, delivering fair and equitable outcomes, and respecting privacy, all while preserving human control. This approach involves multiple stakeholders, such as researchers, developers, business leaders, policy makers, and users, who are affected in various ways by the implementation and evaluation of AI systems. The primary focus of the First Workshop on User Perspectives in Human-Centred Artificial Intelligence (HCAI4U) is to examine the potential positive and negative impacts of automated decision-making systems on end-users, as well as how their interaction with AI is influenced by human-centred aspects of reliability, safety, and fairness. The workshop aims to facilitate discussion and exchange of ideas among the community on advances in developing trustworthy, fair, and privacy-preserving systems, as well as user interfaces that are explainable, with a specific focus on the users' perception in real-world scenarios rather than solely on the algorithmic and model performance. Additionally, HCAI4U aims to foster cross-disciplinary and interdisciplinary discussions between experts from various research fields, such as computer science, psychology, sociology, law, medicine, business, etc., to discuss problems and synergies in this exciting research topic. © 2023 Owner/Author.

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

Predicting Fish Habitat in the Persian Gulf Using Artificial Intelligence 1

引用

International Conference on Advances in Communication Technology and computer Engineering, ICACTCE 2023

作者： Hai, Tao Zhou, Jincheng Ahmadi, Hoorieh Ekiye, Ayibatonbo Ebiare Wei, Yangping Iwendi, Celestine Boulouard, Zakaria School of Computer and Information Qiannan Normal University for Nationalities Guizhou Duyun558000 China School of Creative Technologies University of Bolton Bolton United Kingdom LIM Hassan II University of Casablanca Casablanca Morocco School of Information and Artificial Intelligence Nanchang Institute of Science and Technology Nanchang China

ISBN: (数字)9783031371646

ISBN: (纸本)9783031371639

The Persian Gulf is one of the most important habitats in the Middle East. It can be extremely beneficial to aquatic species’ survival and environmental preservation to continuous monitoring and collect data about aquatic animals, their habitats, and behaviours. Finding a novel and suitable method to carry out accurate and automatic monitoring with low timing and low cost for monitoring aquatic species’ behaviour in this high potential area is helpful. To predict fish habitat in Persian Gulf Convolutional Neural Network method and Naïve Bayes algorithm are used. Deep learning convolutional neural network technology is mostly used for data science classification and recognition because of its exceptional accuracy and to solve search and optimization issues, the Naïve Bayes algorithm is employed. Results indicate for predicting fish habitat in the Persian Gulf, the accuracy of the Convolutional Neural Network algorithm and the Naïve Bayes algorithms is 97.32% and 95.47%, respectively. With p = 0.025 (p0.05), there is a substantial difference between the Naïve Bayes method and the Convolutional Neural Network algorithm. Therefore, The Convolutional Neural Network method seems to be more accurate than the Naïve Bayes method at predicting fish habitat in the Persian Gulf. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Ecosystems

来源：评论

学校读者我要写书评

暂无评论

Face Morphing Attacks and Face Image Quality: The Effect of Morphing and the Unsupervised Attack Detection by Quality

arXiv

引用

arXiv 2022年

作者： Fu, Biying Damer, Naser The Department of Smart Living & Biometric Technologies Fraunhofer Institute for Computer Graphics Research Darmstadt64283 Germany The Department of Computer Science TU Darmstadt Darmstadt64283 Germany

Morphing attacks are a form of presentation attacks that gathered increasing attention in recent years. A morphed image can be successfully verified to multiple identities. This operation, therefore, poses serious security issues related to the ability of a travel or identity document to be verified to belong to multiple persons. Previous works touched on the issue of the quality of morphing attack images, however, with the main goal of quantitatively proofing the realistic appearance of the produced morphing attacks. We theorize that the morphing processes might have an effect on both, the perceptual image quality and the image utility in face recognition (FR) when compared to bona fide samples. Towards investigating this theory, this work provides an extensive analysis of the effect of morphing on face image quality, including both general image quality measures and face image utility measures. This analysis is not limited to a single morphing technique, but rather looks at six different morphing techniques and five different data sources using ten different quality measures. This analysis reveals consistent separability between the quality scores of morphing attack and bona fide samples measured by certain quality measures. Our study goes further to build on this effect and investigate the possibility of performing unsupervised morphing attack detection (MAD) based on quality scores. Our study looks intointra and inter-dataset detectability to evaluate the generalizability of such a detection concept on different morphing techniques and bona fide sources. Our final results point out that a set of quality measures, such as MagFace and CNNNIQA, can be used to perform unsupervised and generalized MAD with a correct classification accuracy of over 70%. © 2022, CC BY.

关键词： Image quality

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：